Causal inference for cloud computing

Cloud computing involves complex technical and economical systems and interactions. This brings about various challenges, two of which are: (1) debugging and control of computing systems, based on heterogeneous data, and (2) prediction of performance and price of spot resources, allocated via auctions. In this paper, we first establish two theoretical results on approximate causal inference. We then use the first one, approximate counterfactuals, along with established causal methodology, to outline a general framework to address (1). To address (2), we show how the second one, approximate integration of causal knowledge, can in principle provide a tool for cloud clients to trade off privacy against predictability of cloud costs. We report experiments on simulated and real data.